© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8058
    Prev
    Next
    INDEX
    Explanations

    broadcasts and telecasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主æĦı
    -0.11
     доÑĢог
    -0.10
     Porn
    -0.08
    èĽĨ
    -0.08
    èĨº
    -0.08
     Cyril
    -0.08
    åį¡éĢļ
    -0.08
    éĴ®
    -0.08
    æµı
    -0.08
    ä½ĺ
    -0.08
    POSITIVE LOGITS
    sWith
    0.12
    ä¸īåĽ½
    0.10
    ted
    0.10
    mmas
    0.09
    åīįå¤ķ
    0.09
    mites
    0.09
    sap
    0.09
    ABLE
    0.09
    å®ļçĤ¹
    0.09
    æĸ°åĮº
    0.08
    Activations Density 0.009%

    No Known Activations